About This Course
Course Description
This course explores how machine learning and AI-driven approaches enhance cleanroom processes across research, development, and production. AI can reduce process variability by identifying time-dependent equipment performance changes and assessing how prior process steps influence current outcomes.
Cornell’s team has applied AI to optimize lithography and etching processes in developing an RF wake-up Nano Electromechanical System (NEMS) switch, which requires precise control of the gap between a moving shuttle and contact. Their work includes an AI model based on decision trees to predict lithography outcomes. This model is now being expanded to plasma etching and combined predictions for lithography and thin-film etching, leveraging CD-SEM imagery for feature extraction and process variable modeling. Additional methods are also in development to train process-modeling CAD tools, enhancing process development efficiency
Course Objectives
- Describes how machine learning and AI-based approaches to research, development, and production bring advantages to cleanroom processes.
- AI-based identification of time-varying equipment performance.
Target Audience
- Managers, supervisors, engineers, technicians, or any individual working directly with this equipment or product
Your Instructors
Google